Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3650 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.4636. Min Act: -0.1700
Data Index: 3100981 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.4636. Min Act: -0.1700
Data Index: 7094735 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.4636. Min Act: -0.1700
Data Index: 763701 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.4323. Min Act: -0.1700
Data Index: 3578207 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.4011. Min Act: -0.1700
Data Index: 8087847 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.4323. Min Act: -0.1700
Data Index: 1046849 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.4011. Min Act: -0.1700
Data Index: 376648 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.4011. Min Act: -0.1700
Data Index: 3783041 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.4011. Min Act: -0.1700
Data Index: 7738024 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.3698. Min Act: -0.1700
Data Index: 3849228 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.4011. Min Act: -0.1700
Data Index: 6812893 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.4011. Min Act: -0.1700
Data Index: 7282067 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.4323. Min Act: -0.1700
Data Index: 4380910 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.3698. Min Act: -0.1700
Data Index: 5888772 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.3698. Min Act: -0.1700
Data Index: 5778098 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.3698. Min Act: -0.1700
Data Index: 7001923 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.3698. Min Act: -0.1700
Data Index: 3100982 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.3698. Min Act: -0.1700
Data Index: 6430196 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.3698. Min Act: -0.1700
Data Index: 6429809 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4636. Min Range: -4.4636
Max Act: 4.4011. Min Act: -0.1700
Data Index: 5893550 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19